Please use this identifier to cite or link to this item:

Title: Information geometric algorithm for estimating switching probabilities in space-varying HMM
Authors: Nascimento, Jacinto
Barão, Miguel
Marques, Jorge S
Lemos, João M
Keywords: Natural Gradient
EM algorithm
Hidden Markov Models
Vector Fields
Issue Date: Dec-2014
Publisher: IEEE
Citation: Jacinto Nascimento, Miguel Barão, Jorge S. Marques, and João M. Lemos. Information geometric algorithm for estimating switching probabilities in space-varying HMM. IEEE Transactions on Image Processing, 23(12):5263–5273, December 2014.
Abstract: This paper proposes an iterative natural gradient algorithm to perform the optimization of switching probabilities in a space-varying hidden Markov model, in the context of human activity recognition in long-range surveillance. The proposed method is a version of the gradient method, developed under an information geometric viewpoint, where the usual Euclidean metric is replaced by a Riemannian metric on the space of transition probabilities. It is shown that the change in metric provides advantages over more traditional approaches, namely: it turns the original constrained optimization into an unconstrained optimization problem; the optimization behaves asymptotically as a Newton method and yields faster convergence than other methods for the same computational complexity; and the natural gradient vector is an actual contravariant vector on the space of probability distributions for which an interpretation as the steepest descent direction is formally correct. Experiments on synthetic and real-world problems, focused on human activity recognition in long-range surveillance settings, show that the proposed methodology compares favorably with the state-of-the-art algorithms developed for the same purpose.
ISSN: 1057-7149
Type: article
Appears in Collections:INF - Publicações - Artigos em Revistas Internacionais Com Arbitragem Científica

Files in This Item:

File Description SizeFormat
accepted.pdf2.57 MBAdobe PDFView/OpenRestrict Access. You can Request a copy!
FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpaceOrkut
Formato BibTex mendeley Endnote Logotipo do DeGóis 

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Dspace Dspace
DSpace Software, version 1.6.2 Copyright © 2002-2008 MIT and Hewlett-Packard - Feedback
UEvora B-On Curriculum DeGois